Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    ingredients and cooking instructions related to recipes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Instructions for combining ingredients

    np_acts-logits-general · gemini-2.0-flash

    carefully filling mixture

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    unlike
    -0.65
     للمعارف
    -0.64
    expandindo
    -0.63
    égard
    -0.60
    发表于
    -0.59
    Crema
    -0.58
     muualla
    -0.57
     StatelessWidget
    -0.56
    whereas
    -0.56
    \{\\
    -0.56
    POSITIVE LOGITS
     gently
    0.71
     evenly
    0.63
     doucement
    0.60
     ensuring
    0.59
     asegur
    0.57
     lightly
    0.57
     Gently
    0.56
     carefully
    0.55
     pastikan
    0.55
     loosely
    0.55
    Act Density 0.266%

    No Known Activations